Recraft V2 is Recraft's foundational image generation model. It delivers photorealistic output, accurate text rendering, and complex prompt following for production design workflows.
import { experimental_generateImage as generateImage } from 'ai';
const result = await generateImage({ model: 'recraft/recraft-v2', prompt: 'A red balloon on a wooden table.'});Recraft V2 is Recraft's original production image generation model. It established the core Recraft capabilities: photorealistic image synthesis, accurate text rendering, and complex prompt following.
Text rendering is a persistent challenge for image generators. Recraft V2 produces legible, correctly spelled text in generated scenes. That makes it useful for signage, labels, or on-image copy. The model also handles multi-clause prompts that specify composition, subject, and style at once.
Recraft V2 serves as the Recraft baseline. Teams already on V2 get stable, predictable output. If you need greater photorealism and style control, Recraft V3 and V4 build on this foundation.